© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15183
    Prev
    Next
    INDEX
    Explanations

    money (million) amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    碰æĴŀ
    -0.20
    åıł
    -0.20
    adora
    -0.20
     verk
    -0.19
    夹
    -0.19
    æ´»
    -0.18
    Caught
    -0.18
    æĸ°çļĦ
    -0.17
    溢
    -0.17
     Hills
    -0.17
    POSITIVE LOGITS
    å¾Ģå¹´
    0.26
    æĺİå¹´
    0.22
    帽
    0.22
     Guerr
    0.21
    nom
    0.21
    nia
    0.20
    ìĭ¬
    0.19
     każ
    0.19
    omat
    0.18
    éķ«
    0.18
    Activations Density 0.006%

    No Known Activations